JP2023030023A - Shelf allocation support device, shelf allocation support method, and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a shelf allocation support device, a shelf allocation support method, and a program that generate a recommended shelf allocation showing a display state of commodities, including a state in which a specific commodity is displayed at a more effective position.

SOLUTION: A shelf allocation support device 10 includes: a generation unit 11 that receives information on a commodity, identifies a commodity indicated by the received information as a specific commodity, and generates a plurality of shelf allocation candidates representing display states of a plurality of commodities including the specific commodity on a commodity shelf; a prediction unit 12 that predicts, on the basis of relation information representing a relation between a positional relation of a commodity on the commodity shelf and sales of a commodity, sales of a specific commodity on the plurality of shelf allocation candidates; and a selection unit 13 that receives a prediction result from the prediction unit and selects a shelf allocation candidate on the basis of the received prediction result.

SELECTED DRAWING: Figure 1

COPYRIGHT: (C)2023,JPO&INPIT

Description

The present invention relates to a planogram support device, a planogram support method, and a program.

In retail stores such as convenience stores and supermarkets, the display positions of products on product shelves are frequently changed because the display positions of products greatly affect sales. In some cases, information such as sales forecast based on the display position of the product is used to change the display position of the product.

Patent Literature 1 describes a method of predicting sales by shelf based on sales prediction information for each product based on actual sales of the product and sales information for each rack of each shelf in the store. .

In Patent Document 2, using the sales order of each product and the sales order of each position of the product shelf, a correspondence relationship condition is set such that products with good sales are displayed at positions with good sales. It is described to display and output the state in which the products are displayed according to the relational conditions.

Further, for example, Patent Document 3 describes a method of simulating product display states using products and PI (Purchase Index) values of the products.

JP 2004-151955 A JP 2010-33114 A JP-A-8-278997

Merchandise sales may vary depending on the position of the shelves on which the merchandise is displayed. Therefore, even if a specific product (for example, a product that a seller wishes to sell) is displayed on a shelf with good sales, the sales of this specific product are not necessarily good.

The techniques of Patent Documents 1 to 3 described above do not consider at all what position it is effective to display this specific product.

SUMMARY OF THE INVENTION The present invention has been made in view of the above problems, and its object is to provide a technique for generating a recommended planogram indicating the display state of products, including the state in which specific products are displayed in more effective positions. to do.

A planogram support device according to an aspect of the present invention receives information about a product, identifies a product indicated by the received information as a specific product, and represents the display state of a plurality of products including the specific product on a product shelf. Predicting the sales of a specific product on a plurality of planogram candidates based on a generating means for generating a plurality of planogram candidates and relationship information representing the relationship between the positional relationship of the products on the product shelf and the sales of the product and predicting means.

Further, in a planogram support method according to an aspect of the present invention, a computer receives information about a product, identifies a product indicated by the received information as a specific product, and stores a plurality of product shelves including the specific product. The system generates multiple planogram candidates that represent the display status of each shelf, and based on the relationship information that shows the relationship between the positional relationship of the product on the shelf and the product sales, the sales of a specific product on the multiple planogram candidates are calculated. Predict.

Further, the program according to an aspect of the present invention receives information about a product, identifies a product indicated by the received information as a specific product, and displays a plurality of products including the specific product on a product shelf. a process of generating planogram candidates and a process of predicting the sales of a specific product on multiple planogram candidates based on relationship information representing the relationship between the positional relationship of products on product shelves and product sales. , is executed by the computer.

A computer program for implementing the above-described device, system, or method by a computer, and a computer-readable non-transitory recording medium storing the computer program are also included in the scope of the present invention.

According to the present invention, it is possible to generate a recommended shelf allocation that indicates the display state of products, including the state in which specific products are displayed in more effective positions.

1 is a functional block diagram showing an example of a functional configuration of a planogram support device according to a first embodiment of the present invention; FIG. It is a figure which shows an example of the whole structure of the planogram support system which concerns on the 2nd Embodiment of this invention. FIG. 10 is a functional block diagram showing an example of the functional configuration of a planogram support device of the planogram support system according to the second embodiment of the present invention; FIG. 10 is a diagram illustrating an example of arrangement candidates generated by a generation unit; FIG. 5 is a diagram showing an example of planogram candidates generated by a generating unit; It is a flowchart which shows an example of the flow of processing of the planogram support apparatus which concerns on the 2nd Embodiment of this invention. FIG. 11 is a functional block diagram showing an example of the functional configuration of a planogram support device according to a third embodiment of the present invention; It is a figure which shows an example of the whole structure of the planogram support system which concerns on the 4th Embodiment of this invention. FIG. 13 is a diagram for explaining a usage scene of the planogram support system according to the fourth embodiment of the present invention; FIG. 11 is a functional block diagram showing an example of the functional configuration of a planogram support device according to a fourth embodiment of the present invention; It is a figure which shows an example of the picked-up image which the imaging device image|photographed. FIG. 11 is a diagram for explaining processing for generating arrangement candidates by a generation unit; FIG. 13 is a flow chart showing an example of the process flow of the planogram support device according to the fourth embodiment of the present invention; FIG. 1 is a diagram illustrating an exemplary hardware configuration of a computer (information processing device) that can implement each embodiment of the present invention; FIG.

<First Embodiment>
A first embodiment of the present invention will be described with reference to the drawings. In this embodiment, a basic configuration for solving the problems of the present invention will be described. FIG. 1 is a functional block diagram showing an example of the functional configuration of a planogram support device 10 according to this embodiment. As shown in FIG. 1 , the planogram support device 10 according to the present embodiment includes a generation unit 11 , a prediction unit 12 and a selection unit 13 .

The generation unit 11 generates a plurality of planogram candidates representing display states of a plurality of products including a specific product on a product shelf. The specific product is, for example, a product that the seller wants to sell via an input unit (not shown), a product that has a large number of inventory, a product that has a close expiration date, an expiration date, or an expiration date. be. Also, the specific item may be all items in stock. The generating unit 11 outputs the generated planogram candidates to the predicting unit 12 .

The prediction unit 12 receives a plurality of planogram candidates from the generation unit 11 . Then, the generation unit 11 predicts the sales of a specific product in a plurality of planogram candidates based on the relationship between the positional relationship between the products displayed on the product shelf and the sales of the product. The relationship between the positional relationship between the products and the sales of the products is represented, for example, by the weight of each shelf for each product name. In addition, the relationship between the positional relationship between the products and the sales of the product may be the weight on each shelf for each product type, the weight on each shelf for each adjacent product name, or the weight on each shelf for each adjacent product type. It is represented by weights in stages. The prediction unit 12 outputs the prediction result to the selection unit 13 .

The selection unit 13 receives prediction results from the prediction unit 12 . Then, the selection unit 13 selects planogram candidates based on the received prediction results. The selection unit 13 selects, for example, a planogram candidate with the highest predicted sales (also referred to as predicted sales) from a plurality of planogram candidates. Here, the magnitude of predicted sales may be the magnitude of the predicted number of sales, or the magnitude of the predicted sales amount.

For example, it is assumed that the predicted sales of product A for a certain planogram candidate (called planogram candidate AA) are 5 and the predicted sales of product B are 4. It is also assumed that the predicted sales of product A for another planogram candidate (called planogram candidate BB) are seven and the predicted sales of product B are one. At this time, the selection unit 13 may calculate the total predicted sales of the product for each planogram candidate and select the planogram candidate AA with the largest total. Further, the selection unit 13 may select the planogram candidate BB, which is the planogram candidate that is the target of the prediction when seven pieces, which are the largest predicted sales, are predicted.

As described above, the planogram support device 10 according to the present embodiment predicts the sales of a specific product based on the relationship between the positional relationship between products and the sales of the product, and calculates the planogram according to the prediction result. Select a candidate.

Therefore, it can be said that the display position of the specific product and the display position relationship between the specific product and other products, which are included in the selected planogram candidates, have an effect on sales. Therefore, according to the planogram support device 10 according to the present embodiment, it is possible to generate a recommended planogram indicating the display state of products, including the state in which specific products are displayed in more effective positions. In addition, since the seller can perform the planogram operation based on the recommended planogram based on the relationship between the position of the product and the sales, the planogram support device 10 according to the present embodiment can perform the planogram operation. We can help you efficiently.

<Second Embodiment>
Next, a second embodiment of the present invention based on the first embodiment described above will be described with reference to the drawings. FIG. 2 is a diagram showing an example of the overall configuration of the planogram support system 1 according to this embodiment. The planogram support system 1 shown in FIG. 2 includes a planogram support device 100 , an inventory management device 200 and a data analysis device 300 . The planogram support device 100 includes the configuration of the planogram support device 10 described above. The planogram support system 1 shown in FIG. 2 shows a configuration unique to the present invention, and even if the planogram support system 1 shown in FIG. 2 has members not shown in FIG. It goes without saying that it is good.

The planogram support device 100, the inventory management device 200, and the data analysis device 300 are connected to each other via a network 400 so as to be able to communicate with each other. Communication means between the devices may be either wired or wireless communication, or via a mobile communication network, a public line network, a LAN (Local Area Network), or a WAN (Wide Area Network). It may be communication. As described above, various methods of communication between the devices can be considered, but since they are not related to the essence of the present embodiment, detailed description thereof will be omitted.

The inventory management device 200 manages the inventory of products in the store. The inventory management device 200 receives sales data indicating sales for each product name from one or more POS (Point Of Sales) terminals 21, and manages inventory based on the received sales data and order data. The order data may be transmitted from an ordering device (not shown).

Although FIG. 2 shows a configuration in which the inventory management device 200 is installed in each store, the inventory management device 200 may be a server installed in a location other than the store. In this case, the inventory management device 200 manages the inventory of multiple stores for each store. Also, the inventory management device 200 may be integrated with the POS terminal 21 . Here, the sales data is, for example, general POS data such as the sales amount and number of sales of a certain product, but the present embodiment is not limited to this. In addition, it is assumed that the inventory information managed by the inventory management device 200 includes product names, quantities, product types, etc., but the present embodiment is not limited to this. may include the product's expiration date (use-by date, consumption-by date, or best-before date). The inventory management device 200 transmits information about inventory to be managed to the planogram support device 100 .

The data analysis device 300 is a device that analyzes the relationship between the positional relationship between products and the sales of the products. The data analysis device 300 analyzes the relationship between the positional relationship between the products and the sales of the products, for example, based on the captured image and the sales data. Hereinafter, a method for analyzing the relationship between the positional relationship between products and the sales of products by the data analysis device 300 will be described. may

Data analysis apparatus 300 in the present embodiment uses photographed images of product shelves as learning data, and recognizes products included in the photographed images. Then, the data analysis device 300 identifies the arrangement position of the recognized product on the product shelf. The data analysis device 300 also receives sales data indicating sales for each product name from the POS terminal 21, for example. The sales data received by the data analysis device 300 from the POS terminal 21 may be the same as the sales data received by the inventory management device 200, or the sales data received by the inventory management device 200 may be dated differently. It may be data. The sales data received by the data analysis device 300 may be data that can be used when analyzing the relationship between the positional relationship between products and the sales of the products.

The data analysis device 300 analyzes the relationship between the positional relationship between the products and the sales of the products based on the identified product placement positions and the sales data of the products. Below, the analysis result analyzed by the data analysis device 300 is also referred to as relationship information.

For example, the data analysis device 300 uses information indicating the recognized product (for example, the product name) and the arrangement position of the recognized product on the product shelf to identify the product name and the shelf level of the product shelf. It is converted into a feature vector f (product name, shelf level) to be used as a variable. For example, it is assumed that each component of the feature vector f is represented by the number of arrangements in which a product is arranged in a row. In other words, "f(product A, 1)=1" indicates that one product whose product name is "product A" is arranged on the first stage of the product shelf. In the following description, for example, f (merchandise A, 1) is referred to as f _A1 .

The data analysis device 300 uses this feature vector f to perform data analysis for each product name. Data analysis for a product whose product name is “product A” will be described below. The feature amount vector of product A is described as f _A. It is also assumed that the analysis data used for data analysis are the following (1) and (2).
(1) Feature vector f _A =(f _A1 , f _A2 , f _A3 , f _A4 , f _A5 )=(1, 0, 0, 2, 2) for product A in a store, and product A in the same store A dataset containing sales (y _A )=1000 for .
(2) Feature vector f _A =(f _A1 , f _A2 , f _A3 , f _A4 , f _A5 )=(0, 3, 1, 4, 0) for product A at another store, and product at the same store Data set containing sales to A (y _A )=3000.

Note that the analysis data is not limited to two sets, and may be multiple sets. In this embodiment, two sets of data from different stores are used as an example, but a data set generated from sales data of one store on different dates and times may be used.

A feature vector f _A for product A has components for the number of stages of product shelves. The value of each component indicates the number of products arranged, as described above. From the above (1), in a product shelf arranged in a certain store, one product A is placed on the first level of the product shelf, and is not placed on the second and third levels. , are arranged in each of the fourth and fifth stages.

The data analysis device 300 uses this analysis data to calculate θ _A that satisfies the following equation (1).

In equation (1), i denotes a shelf level (i=1, 2, 3, 4, 5).

The data analysis device 300 uses the analysis data to obtain θ _A that is the result of data analysis (analysis result), for example, θ _A =(f _A1 , f _A2 , f _A3 , f _A4 , f _A5 ) = (500, 800, 100, 400, 100). Each component θ _Ai of θ _A , which is the analysis result in the present embodiment, indicates the weight of each rack level of the product A on the product shelf. A component with a higher weight indicates a shelf with higher sales of product A. Therefore, in the example of the above analysis result, it can be seen that product A is the highest when placed on the second stage. As described above, the data analysis device 300 identifies the position of the rack with the highest sales for each product name.

One or a plurality of products of one or a plurality of types are displayed on a product shelf 20 having a plurality of shelves as shown in FIG. Further, on the product shelf 20, a product having a certain product name and another product having the same product name or a different product name are often displayed vertically or horizontally side by side. The product shelf 20 includes a plurality of products displayed on each shelf in this manner. Therefore, this weight takes into account the relationship between the positional relationship between the products displayed on a certain shelf and the products displayed on another shelf, and the sales of the products.

In the data analysis apparatus 300 according to the present embodiment, the sales amount is used as the value of _yA used for analysis, but the number of sales may be used, for example. At this time, if the sales data includes the sales amount of the product and the unit price of the product, but does not include the number of sales, the data analysis device 300 obtains the number of sales by dividing the sales by the unit price. , the number of sales may be used as the value of _yA .

Further, the data analysis device 300 may use a regression analysis method such as the least squares method as shown in Equation (1), or may use a classification method as an analysis method.

For example, when the above-described _yA is a specific value such as the sales amount or the number of sales, the data analysis device 300 preferably performs analysis using a regression analysis technique. As the regression analysis method, other than the least squares method described above, for example, linear regression, maximum likelihood method, Bayesian linear regression, neural network, or the like may be used.

Also, when y _A indicates the degree of sales, for example, the data analysis device 300 preferably uses a classification technique to analyze. The case where the degree of sales is indicated is, for example, the case where _yA is a value indicated in 10 levels from 1 to 10 according to the sales. As a classification technique, for example, a generative model such as Naive Bayes, logistic regression, support vector machine, neural network, nearest neighbor classification, decision tree, or the like may be used. In this way, the data analysis device 300 can appropriately select an analysis method depending on the contents of the learning data (for example, the type of value of y).

As described above, the analysis result output by the data analysis device 300 indicates the weight of each shelf of the product shelf 20 shown in FIG. 2 for each product name. The analysis result output by the data analysis device 300 is not limited to each product name, and may be, for example, the weight of each shelf for each product type, each adjacent product name, and each adjacent product type. Further, the analysis result output by the data analysis device 300 may be a weight for adjacent products adjacent to the product indicated by the product name for each product name. The analysis result may be a combination of these. Further, the adjacent product is a product that is adjacent to at least one of the left and right or a product that is adjacent to at least one of the top and bottom within a predetermined range.

The data analysis device 300 transmits the analysis result to the planogram support device 100 as relationship information representing the relationship between the positional relationship between the products and the sales of the products. The data analysis device 300 may be integrated with the planogram support device 100 as an analysis unit.

(Planogram support device 100)
FIG. 3 is a functional block diagram showing an example of the functional configuration of the planogram support device 100 of the planogram support system 1 according to the present embodiment. 3 shows a configuration unique to the present invention, and needless to say, the planogram support device 100 shown in FIG. 3 may have members not shown in FIG.

The planogram support device 100 includes a generation unit 110, a prediction unit 120, a selection unit 130, an inventory information storage unit 140, and a relationship information storage unit 150, as shown in FIG. Note that the inventory information storage unit 140 and the relationship information storage unit 150 may be realized by one storage unit. Moreover, the inventory information storage unit 140 and the relationship information storage unit 150 may each be realized by a storage device separate from the planogram support device 100 .

The inventory information storage unit 140 stores information on inventory (inventory information) transmitted from the inventory management device 200 . The relationship information storage unit 150 stores relationship information transmitted from the data analysis device 300 . Note that the planogram support device 100 does not have to include the inventory information storage unit 140 and the relationship information storage unit 150 . In this case, the planogram support device 100 may be configured to communicate with the inventory management device 200 and the data analysis device 300 and acquire information necessary for the processing described later.

The generating unit 110 receives, for example, through an input unit (not shown) information about a product that the seller wants to sell, and identifies the product indicated by the received information as a specific product. Further, the generating unit 110 may refer to the inventory information storage unit 140, and, for example, may select a product with a large number of stocks or a product with a near expiry date, expiration date, or expiration date as a specific product. Also, the specific item may be all items in stock.

The generating unit 110 generates a candidate product to be placed in a position where the one or more specific products can be placed on a product shelf, and the candidate product includes at least one specific product. to generate For example, assume that product A is a specific product and the product shelf on which the product is displayed is a two-level product shelf with two slots on each shelf level. Then, assuming that the first row is the position where product A can be placed, the generation unit 110 generates a product candidate to be placed in this position where product A can be placed as a placement candidate. In the present embodiment, the specific product is one product A, so generation unit 110 includes product A in the placement candidates. At this time, the generation unit 110 generates placement candidates for all possible placement positions (round-robin). In this example, as described above, the possible placement positions are the 1st slot of the 1st stage (hereinafter referred to as (1, 1)) and the 2nd slot of the 1st stage (hereinafter referred to as (1, 2) ), the generation unit 110 generates layout candidates for these two locations. In the case of this example, since there are two possible positions, the number of products that can be arranged at these possible positions is two. Therefore, the generation unit 110 generates layout candidates such that at least one of the two is product A. FIG.

FIG. 4 shows examples of specific placement candidates. The generation unit 110 generates placement candidates for products, including product A, to be placed in positions where placement is possible, as shown in FIG. 4 . In addition, in FIG. 4, x shows goods other than the goods A. As shown in FIG. If there are four types of products other than product A, namely product B, product C, and product D, x is one of B, C, and D. In this way, the generation unit 110 generates, in a round-robin fashion, placement candidates for products, including a specific product, to be placed in positions where placement is possible.

Then, the generation unit 110 generates a plurality of planogram candidates representing the states of the products displayed on the product shelf 20 . For example, when stock products other than product A are product B, product C, and product D, the generating unit 110 generates planogram candidates as shown in FIG. As described above, product A, which is a specific product, is included in the possible layout positions. Therefore, it can be said that the generation unit 110 generates a planogram candidate representing a state in which a plurality of products including the product A are displayed on the product shelf 20 .

The planogram candidates shown in FIG. 5 show one example of the planogram candidate including the layout candidate (1) in FIG. 4 and one example of the planogram candidate including the layout candidate (3) in FIG. In the present embodiment, generation unit 110 combines display positions of inventory products with respect to positions (in FIG. 4, the second row) other than positions where products are arranged (possible positions) indicated by arrangement candidates. are obtained (in round robin), and planogram candidates are generated based on the obtained combinations. Here, as described above, the inventory products are the products B to D. Therefore, the generation unit 110 creates a combination of products to be arranged in each slot on the second stage of the product shelf. Generate for In addition, the product to be arranged at positions other than the position where arrangement is possible may be one type of product, or may be different types of products. In addition, a specific product (in this case, product A) may be included in the products to be arranged at positions other than the position where arrangement is possible.

Note that the positions where a specific product can be arranged may be all the slots of all the shelves of the product shelf. In this case, the generation unit 110 outputs the generated placement candidates as planogram candidates.

The generation unit 110 outputs the plurality of generated planogram candidates to the prediction unit 120 together with specific product information indicating a specific product (product A in the above example).

The prediction unit 120 receives the plurality of planogram candidates generated by the generation unit 110 together with the specific product information from the generation unit 110 . Based on the relationship information in the relationship information storage unit 150, the prediction unit 120 predicts the sales of the product indicated by the received specific product information for each of the received planogram candidates.

As described above, the relationship information is information as shown in (1) to (5) below.
(1) Weight on each shelf for each product name,
(2) Weight on each shelf for each product type,
(3) weight on each shelf for each adjacent product name;
(4) Weight on each shelf for each adjacent product type,
(5) Weight for adjacent products adjacent to the product indicated by the product name for each product name.

Note that the relationship information may be a combination of (1) to (5).

For example, in the case of "planogram candidate (1)-1" shown in FIG. 5, product A is on the first stage. Assume that the relationship information θ _A indicated by (1) above is θ _A =(0.9, 0.5). This relationship information θ _A indicates the weight of product A on each shelf level, and indicates that the weight of the first level is 0.9 and the weight of the second level is 0.5. The prediction unit 120 predicts the sales of product A in this planogram candidate (1)-1 using the relationship information _θA . In the case of "planogram candidate (1)-1" shown in FIG. 5, product A is in the first row, so the sales of product A are predicted using the weight of 0.9 in the first row. .

Further, for example, in the case of "planogram candidate (1)-1" shown in FIG. 5, the product B is adjacent to product A on the right. Then, if the relationship information θ indicated by the above (3) is θ=(adjacent product name, weight in first row, weight in second row)=(product B, 0.3, 0.2) do. This relationship information θ indicates that the weight on the first level is 0.3 and the weight on the second level is 0.2 when the product name of the adjacent product is product name B. The prediction unit 120 predicts the sales of product A in this planogram candidate (1)-1 using the relationship information θ. In the case of "planogram candidate (1)-1" shown in FIG. 5, the adjacent product name is product B, and product B is in the first row, so the sales of product A is the weight of the first row. Predicted using 0.3.

Also, for example, if the relationship information θ _A indicated by the above (5) is θ _A = (adjacent product weight of product A, adjacent product weight of product B, adjacent product weight of product C, adjacent product weight of product D weight)=(0.5, 0.7, 0.3, 0.8). This relationship information θ _A indicates that the weight is 0.5 when the adjacent product of product A is product A, and the weight is 0.7 when product B is the adjacent product of product A. ing. Similarly, this relationship information θ _A has a weight of 0.3 when the adjacent product of product A is product C, and a weight of 0.8 when product D is the adjacent product of product A. It is shown that. As a result, it can be seen that the weight is the highest when the product D is adjacent to the product A. The prediction unit 120 predicts the sales of product A in this planogram candidate (1)-1 using the relationship information _θA . For example, in the case of "planogram candidate (1)-1" shown in FIG. 5, the product adjacent to the right of product A is product B, so the sales of product A are that product B is next to product A. It is predicted using a case weight of 0.7.

After that, the prediction unit 120 predicts the sales of product A for all planogram candidates. The relationship information based on which the prediction unit 120 makes a prediction may be any one of (1) to (5) described above, or may be plural.

The prediction unit 120 outputs the predicted sales for each planogram candidate to the selection unit 130 as a prediction result.

The selection unit 130 receives prediction results from the prediction unit 120 . Then, the selection unit 130 selects the planogram candidate with the highest sales from the plurality of planogram candidates based on the received prediction result. For example, if the sales of product A in "planogram candidate (1)-1", "planogram candidate (1)-2", and "planogram candidate (1)-3" are 50, 100, and 150, respectively. , the selection unit 130 selects "planogram candidate (1)-3" with the highest sales. As a result, the product display state that is more effective for sales of product A is that product A is displayed in the first slot of the first shelf, product D is displayed to the right of product A, and product D is displayed below product A. It can be seen that the product C is displayed at . The selection unit 130 can output the selected planogram candidate as a recommended planogram indicating the display state of the product, including the state in which the specific product is displayed in a more effective position.

(Processing flow of planogram support device 100)
Next, the flow of processing in the planogram support device 100 will be described. FIG. 6 is a flow chart showing an example of the flow of processing in the planogram support device 100 according to the present embodiment.

As shown in FIG. 6, the generation unit 110 generates placement candidates, which are product candidates including a specific product, to be arranged at possible positions on the product shelf (step S61). Then, the generation unit 110 generates a plurality of planogram candidates including the state in which the specific product is arranged in the arrangement possible positions indicated by the generated arrangement candidates (step S62).

Based on the relationship information, the prediction unit 120 predicts the sales of specific products for each of the plurality of planogram candidates generated in step S62 (step S63).

After that, the selection unit 130 selects the planogram candidate with the highest sales among the plurality of planogram candidates based on the predicted sales (prediction result) of the specific product for each planogram candidate (step S64).

With this, the recommended planogram generation processing in the planogram support apparatus 100 according to the present embodiment is completed.

(effect)
As described above, in the planogram support device 100 according to the present embodiment, the generation unit 110 selects product candidates to be arranged at positions where one or more specific products can be arranged, and at least one specific product Generate placement candidates that indicate candidates that contain products. Then, the generation unit 110 generates display states of a plurality of products including a specific product on the product shelf, including a state in which at least one specific product is arranged in an arrangement possible position, which is a state indicated by the generated arrangement candidates. Generate planogram candidates to represent Then, the prediction unit 120 predicts specific products in each of the plurality of planogram candidates generated based on the relationship information representing the relationship between the positional relationship between the products displayed on the product shelf and the sales of the products. predict the sales of After that, the selection unit 130 selects the planogram candidate with the highest predicted sales from the plurality of planogram candidates based on the prediction results.

Since the prediction unit 120 predicts the sales of a specific product based on the relationship information, this prediction result can predict the sales according to the display positions of a plurality of products including the specific product. In addition, it can be said that the planogram candidate with the highest predicted sales has a greater effect on sales due to the relationship between the display positions of the specific product and the other products.

Therefore, according to the planogram support device according to the present embodiment, it is possible to generate a recommended planogram indicating the display state of products, including the state in which specific products are displayed in more effective positions. Therefore, the planogram support device 100 according to the present embodiment can efficiently support the planogram work in the same manner as the planogram support device 10 in the first embodiment described above.

(Modification)
A modified example of the relationship information will be described in the modified example of the present embodiment.

Depending on the store, for example, there are cases where products with a near expiry date or the like are discounted. Therefore, the data analysis device 300 may analyze the products based on information such as products whose expiration dates are approaching and products with discounts. For example, when another product adjacent to a certain product (adjacent product) is due soon, the data analysis device 300 analyzes the relationship between the positional relationship between this product and the adjacent product and the sales of the product. You can The data analysis device 300 may also analyze the sales on each shelf for each product whose deadline is near and output it as relationship information.

Then, the prediction unit 120 may predict sales based on the relationship information output by the data analysis device 300, like the prediction unit 120 in the second embodiment described above.

Even with such a configuration, the planogram support device 100 according to this modification can achieve the same effects as the planogram support device 100 in the above-described second embodiment.

Moreover, in the second embodiment, the prediction unit 120 predicts sales of a specific product, but sales of other products may also be calculated. Then, for example, when there are a plurality of planogram candidates with the highest predicted sales, the selection unit 130 may select the planogram candidate with the highest sales of all products included in the planogram candidates.

Even with such a configuration, the planogram support device 100 can generate a recommended planogram indicating the display state of the product, including the state in which the specific product is displayed in a more effective position.

<Third Embodiment>
Next, a third embodiment of the invention will be described with reference to the drawings. FIG. 7 is a functional block diagram showing the functional configuration of the planogram support device 101 in the planogram support system 1 according to the present embodiment. For convenience of explanation, members having the same functions as members included in the drawings described in the second embodiment are denoted by the same reference numerals, and description thereof will be omitted. Further, since the overall configuration of the planogram support system 1 according to the present embodiment is the same as the configuration of the planogram support system 1 according to the second embodiment shown in FIG. 2, description thereof will be omitted.

As shown in FIG. 7, the planogram support device 101 includes a generation unit 111, a prediction unit 120, a selection unit 130, an inventory information storage unit 140, a relationship information storage unit 150, and a template storage unit 160. . The planogram support device 101 shown in FIG. 7 also includes an analysis unit 301 corresponding to the data analysis device 300 . Note that the analysis unit 301 has the same functions as the data analysis device 300, so the description thereof will be omitted. By providing the planogram support device 101 with an analysis function, it is possible to reduce the network load on the communication of relationship information.

Note that the inventory information storage unit 140, the relationship information storage unit 150, and the template storage unit 160 may be realized by one storage unit. Also, the inventory information storage unit 140, the relationship information storage unit 150, and the template storage unit 160 may each be realized by a storage device separate from the planogram support device 101. FIG.

The template storage unit 160 stores, as templates, information indicating product display states in each of a plurality of stores. Further, the template storage unit 160 may store, as a template, information indicating a product display state recommended by the headquarters of the chain store, for example.

The generation unit 111 generates placement candidates including at least one of the specific products to be arranged in the position where the specific product on the product shelf 20 can be arranged, based on the template stored in the template storage unit 160. to generate. First, the generation unit 111 identifies a specific product in the same manner as the generation unit 110 described above. Then, the generating unit 111 generates, based on the template, placement candidates, which are product candidates to be placed in positions where the one or more specific products can be placed. For example, assume that product A is a specific product and the product shelf on which the product is displayed is a two-level product shelf with two slots on each shelf level. Assume that the first row is the position where product A can be arranged. Here, the template includes information indicating the state in which (product A, product A), (product A, product B), and (product C, product A) are arranged in each slot on the first level. Suppose that Note that the state in which (the product C and the product A) are arranged means that the product C is arranged in the first slot of the first stage and the product A is arranged in the second slot. In this case, the generator 111 generates layout candidates based on this template. Based on the template, the generation unit 111 may set all of the above-described (product A, product A), (product A, product B), and (product C, product A) as arrangement candidates, or may select any one of them. It may be used as an arrangement candidate.

Then, the generation unit 111 generates a plurality of planogram candidates representing the states in which the products are arranged on the product shelf 20 . As described above, this planogram candidate includes a state in which product A is placed in at least one of the slots of possible placement positions. When there are a plurality of specific products, the planogram candidates include a state in which at least one specific product is placed in at least one slot of the possible positions. The generation unit 111 determines a combination of display positions of stock products other than the product A based on templates stored in the template storage unit 160 . Note that the present embodiment is not limited to this, and the generation unit 111 may determine the combination of display positions of the inventory products other than the product A by round robin as in the second embodiment described above. good. Then, the generation unit 111 generates planogram candidates based on the determined combination.

As in the second embodiment, the generation unit 111 obtains placement candidates for all positions where a specific product can be placed (by round robin), and displays inventory products other than the specific product. Position combinations may be determined based on templates stored in template storage 160 .

Note that the positions where a specific product can be arranged may be all the slots of all the shelves of the product shelf. In this case, the generating unit 111 outputs the layout candidate generated based on the template as the planogram candidate.

After that, as in the second embodiment, the prediction unit 120 predicts the sales of a specific product for each of the plurality of planogram candidates, and the selection unit 130 predicts the planogram based on the prediction results. Select a candidate.

As described above, the planogram support device 101 according to the present embodiment can obtain the same effects as the planogram support device 100 according to the second embodiment described above. As described above, the planogram support apparatus 101 according to the present embodiment generates a plurality of planogram candidates using templates prepared in advance. As a result, compared to the planogram support apparatus 100 according to the second embodiment described above, it is possible to reduce the processing amount of the planogram candidate generation processing and the processing amount of the sales forecast processing, etc. The load on the device 101 can be reduced.

<Fourth Embodiment>
Next, a fourth embodiment of the present invention will be described with reference to the drawings. FIG. 8 is a diagram showing an example of the overall configuration of the planogram support system 2 according to this embodiment. For convenience of explanation, members having the same functions as members included in the drawings described in each of the above-described embodiments are denoted by the same reference numerals, and descriptions thereof are omitted.

The planogram support system 2 shown in FIG. 8 includes a planogram support device 102 , an inventory management device 200 , a data analysis device 300 and an imaging device 500 . FIG. 9 is a diagram for explaining usage scenes of the planogram support system 2 according to the present embodiment. FIG. 9 is a functional block diagram showing an example of the functional configuration of the planogram support system 2 according to this embodiment.

In the planogram support system 2 according to the present embodiment, the imaging device 500 captures the product displayed on the product shelf 20 of the store and transmits the captured image to the planogram support device 102 .

As shown in FIG. 9, the imaging device 500 may be, for example, a terminal equipped with an imaging function such as a mobile phone terminal, a smart phone, a digital camera, or a tablet, or may be a surveillance camera installed in a store. good. If the product shelf 20 photographed by the imaging device 500 has a place where no product is displayed (called an empty slot), the planogram support device 102 outputs a recommended planogram for the product shelf 20 . As a result, the worker who displays the products can display the products effective for sales in the empty slots by checking the recommended planogram on the display device (not shown). In this way, the planogram support system 2 efficiently supports the planogram work of selecting products to be displayed in empty slots.

Next, with reference to FIG. 10, the functional configuration of the planogram support device 102 in the planogram support system 2 according to the present embodiment will be described. FIG. 10 is a functional block diagram showing an example of the functional configuration of the planogram support device 102 according to this embodiment. As shown in FIG. 10, the planogram support device 102 in this embodiment includes a generation unit 112, a prediction unit 120, a selection unit 130, an inventory information storage unit 140, a relationship information storage unit 150, and a recognition unit. 170 and a product information storage unit 180 . The inventory information storage unit 140, the relationship information storage unit 150, and the product information storage unit 180 may be realized by one storage unit. Further, the inventory information storage unit 140, the relationship information storage unit 150, and the product information storage unit 180 may each be realized by a storage device separate from the planogram support device 102. FIG.

The product information storage unit 180 stores information for recognizing products included in images captured by the imaging device 500 . Specifically, the product information storage unit 180 stores the product image (also referred to as a master image) and/or the feature amount included in the product image that identifies the product (for example, a product identifier, product name, etc.) and stored.

The recognition unit 170 receives the captured image of the product shelf 20 captured by the imaging device 500 from the imaging device 500 . Then, the recognition unit 170 refers to the information for recognizing the product stored in the product information storage unit 180, and recognizes the product included in the photographed image from the photographed image. The method by which the recognition unit 170 recognizes the product may use, for example, a local feature amount, template, brightness, edge, outline, shape, color information, depth, etc., or may use other information. may The method by which the recognition unit 170 recognizes the product is not particularly limited, and a general recognition method may be used, so detailed description is omitted in this specification. Then, the recognition unit 170 outputs, as a recognition result, information identifying the recognized product (for example, product identifier, product name, etc.) and information indicating the position of the product on the photographed image (for example, coordinate values in the photographed image). is output to the generation unit 112 . FIG. 11 shows an example of a captured image. The captured image is, for example, an image as shown in FIG. The product shelf 20 included in the photographed image has four shelf levels, and the number of products (the number of slots) that can be placed on each shelf level is four. A plurality of products are displayed in the product shelf 20 of FIG. The alphabet in each product shown in FIG. 11 indicates the last character of the product name. In FIG. 11, for example, a product whose product name is “product A” is indicated as “A”.

The recognition unit 170 recognizes the product from this photographed image. Then, the recognition unit 170 outputs the recognition result to the generation unit 112 together with the captured image.

Note that the recognition unit 170 may be realized by a device separate from the planogram support device 102 . In this case, the planogram support device 102 receives the recognition result from the separate device. As a result, the planogram support device 102 can reduce the processing load on the planogram support device 102 . In addition, by providing the planogram support device 102 with the recognition unit 170, the network load associated with transmission and reception of recognition results can be reduced.

The generation unit 112 receives the product recognition result from the recognition unit 170 together with the photographed image. Then, the generation unit 112 determines the position where the product is not displayed from the captured image. That is, the generation unit 112 identifies empty slots from the captured image. Note that the identification of this empty slot may be performed by the recognition unit 170 . In this case, the recognition unit 170 may transmit information indicating the position of the empty slot together with the product recognition result. In the case of the captured image shown in FIG. 11, the generation unit 112 identifies the third slot in the second row and the fourth slot in the second row as empty slots.

This empty slot is a position where a product can be placed. Therefore, the generation unit 112 generates candidates for products to be placed in the empty slots, which include at least one of one or more specific products. This will be explained using FIG. FIG. 12 is a diagram for explaining the arrangement candidate generation processing by the generation unit 112 . As shown in FIG. 12, in this embodiment, it is assumed that specific products are products that the seller wants to sell, and that the products are product L, product M, and product N. Note that the specific product may be all the products in stock managed by the inventory management device 200 .

The generation unit 112 generates placement candidates, which are candidates for arranging a specific product in this empty slot. For convenience of explanation, the arrangement candidates shown in FIG. 12 are shown so as to correspond to two empty slots in the product shelf.

The generation unit 112 generates, as a placement candidate, any combination of specific products to be placed in each of the two slots that are available positions. FIG. 12 shows nine placement candidates. In FIG. 12, the empty slot on the left side indicates the third slot on the second stage in FIG. 11, and the empty slot on the right side indicates the fourth slot on the second stage in FIG. For example, among the arrangement candidates shown in FIG. 12, the upper left arrangement candidate indicates that the combination of products to be arranged in the third slot on the second level and the fourth slot on the second level in the product shelf 20 is (product L, product L). In other words, the upper left placement candidates indicate that both of the product candidates to be placed in the third and fourth slots on the second level of the product shelf 20 are product L. FIG.

Note that the arrangement candidates shown in FIG. 12 are a combination of specific products to be arranged in each of the two slots that can be arranged, but the present embodiment is not limited to this. The generating unit 112 only needs to include a specific product among the products to be placed in one of the two slots that are available positions. For example, the generation unit 112 may set the combination of products to be placed in the third slot of the second row and the fourth slot of the second row as (product L, product A). This product A is a stock product that is not a specific product. In addition, when there is only one slot available for placement, the generation unit 112 sets any of the specific products as a placement candidate.

Note that the generation unit 112 may generate placement candidates for all possible placement positions (round-robin), as in the second embodiment. Moreover, the generating unit 112 may generate based on a template, as in the third embodiment. In this case, the planogram support device 102 may be configured to include the template storage unit 160, like the planogram support device 101 in the third embodiment.

Then, the generation unit 112 arranges at least one of the specific products in the arrangement possible position based on the generated arrangement candidates, and places the recognized product in the position corresponding to the position in the photographed image of the recognized product. Generate a planogram candidate that represents the state of arranging On the first stage of the product shelf 20 included in the photographed image shown in FIG. 11, product A, product A, product B, and product B are arranged in order from the left. The recognition unit 170 recognizes these products and their positions from the captured images. Therefore, the generation unit 112 sets the state of the first stage included in the shelving allocation candidates as a state in which product A, product A, product B, and product B are arranged in order from the left. Similarly, the generation unit 112 determines the products to be placed on other racks based on the recognition results.

The generation unit 112 then outputs the generated planogram candidate to the prediction unit 120 .

After that, as in the second embodiment, the prediction unit 120 predicts the sales of a specific product for each of the plurality of planogram candidates, and the selection unit 130 predicts the planogram based on the prediction result. Select a candidate.

(Processing flow of planogram support device 102)
Next, the flow of processing in the planogram support device 102 will be described. FIG. 13 is a flow chart showing an example of the flow of processing in the planogram support device 102 according to this embodiment.

As shown in FIG. 13, first, the recognition unit 170 receives a photographed image of a product shelf photographed by the imaging device 500 (step S131). Then, the recognition unit 170 recognizes the product from the received photographed image (step S132).

After that, the generation unit 112 generates placement candidates, which are product candidates including a specific product, to be arranged at a position (arrangeable position) determined by the recognition unit 170 that no product is displayed (step S133). ). Then, the generation unit 112 arranges the specific product indicated by the generated arrangement candidate at the position where the product can be arranged, and places the recognized product at the position corresponding to the position in the photographed image of the product recognized from the photographed image. is generated (step S134).

Based on the relationship information, the prediction unit 120 predicts the sales of specific products for each of the plurality of planogram candidates generated in step S134 (step S135).

After that, the selection unit 130 selects the planogram candidate with the highest sales among the plurality of planogram candidates based on the predicted sales (prediction result) of the specific product for each planogram candidate (step S136).

With this, the recommended planogram generation processing in the planogram support device 102 according to the present embodiment is completed.

As described above, according to the planogram support system 2 according to the present embodiment, as in each of the above-described embodiments, the product display state including the state in which the specific product is displayed in a more effective position A recommended planogram showing the Therefore, the planogram support system 2 according to the present embodiment can efficiently support the planogram work as in the above-described embodiments.

<Hardware configuration example>
Here, an example of the configuration of hardware capable of realizing the planogram support apparatus (10, 100 to 102) according to each of the above-described embodiments will be described. The planogram support devices (10, 100 to 102) described above may be implemented as dedicated devices, or may be implemented using a computer (information processing device).

FIG. 14 is a diagram illustrating the hardware configuration of a computer (information processing device) that can implement each embodiment of the present invention.

The hardware of the information processing apparatus (computer) 90 shown in FIG. Random Access Memory) 95 , a storage device 97 , and a drive device 98 for computer-readable storage media 99 , which are connected via a bus 96 . The input/output user interface 93 is a man-machine interface such as a keyboard as an example of an input device and a display as an output device. The communication interface 92 is general communication means for the devices (FIGS. 1, 3, 7 and 10) according to the above-described embodiments to communicate with external devices via the communication network 80 . In this hardware configuration, the CPU 91 controls the overall operation of the information processing device 90 that implements the planogram support device (10, 100 to 102) according to each embodiment.

The present invention, which has been described with the above-described embodiments as examples, supplies a program (computer program) capable of implementing the processing described in each of the above-described embodiments to the information processing apparatus 90 shown in FIG. After that, the program is read out to the CPU 91 and executed. Note that such a program may be, for example, the various processes described in the flowcharts (FIGS. 6 and 13) referred to in the description of the above embodiments, or the apparatus in the block diagrams shown in FIGS. It may be a program capable of realizing each part (each block) shown in the inside.

Also, the program supplied to the information processing device 90 may be stored in a readable/writable temporary memory (95) or a non-volatile storage device (97) such as a hard disk drive. That is, in the storage device 97, the program group 97A is, for example, programs capable of realizing the functions of the units shown in the planogram support device (10, 100 to 102) in each of the above-described embodiments. Various types of stored information 97B are, for example, planogram candidates, relationship information, inventory information, photographed images, recognition results, templates, recommended planograms, and the like in each of the above-described embodiments. However, when implementing the program in the information processing device 90, the constituent units of the individual program modules are not limited to the division of each block shown in the block diagram, and may be appropriately selected by those skilled in the art upon implementation.

In the above case, the method of supplying the program into the device is to install it in the device via various computer-readable recording media (99) such as CD (Compact Disk)-ROM, flash memory, etc. At present, general procedures can be adopted, such as a method, a method of downloading from the outside via a communication line (80) such as the Internet, and the like. In such a case, the present invention can be considered to be constituted by the code (program group 97A) constituting such a computer program or the storage medium (99) storing such code.

In each of the embodiments described above, the case where the functions shown in the blocks shown in the block diagram are realized by a software program as an example of execution by the CPU 95 shown in FIG. 14 has been described. However, some or all of the functions shown in each block shown in the block diagram may be implemented as hardware circuits.

The above-described embodiments are preferred embodiments of the present invention, and the scope of the present invention is not limited only to the above-described embodiments. can be modified or substituted for each of the above-described embodiments, and various modified forms can be constructed.

This application claims priority based on Japanese Patent Application No. 2015-116477 filed on June 9, 2015, and the entire disclosure thereof is incorporated herein.

1 Planogram allocation support system 2 Planogram allocation support system 10 Planogram allocation support device 11 Generation unit 12 Prediction unit 13 Selection unit 100 Planogram allocation support device 101 Planogram allocation support device 102 Planogram allocation support device 110 Generation unit 111 Generation unit 112 Generation unit 120 Prediction Part 130 Selection Part 140 Inventory Information Storage Part 150 Relationship Information Storage Part 160 Template Storage Part 170 Recognition Part 180 Product Information Storage Part 200 Inventory Management Device 300 Data Analysis Device 301 Analysis Part 400 Network 500 Imaging Device 20 Product Shelf 21 POS Terminal

Claims (7)

generating means for receiving information about a product, identifying the product indicated by the received information as a specific product, and generating a plurality of planogram candidates representing display states of a plurality of products including the specific product on a product shelf; ,
prediction means for predicting the sales of the specific product on the plurality of planogram candidates based on relationship information representing the relationship between the positional relationship of the product on the product shelf and the sales of the product;
planogram support device. 2. The planogram support apparatus according to claim 1, further comprising selection means for selecting a planogram candidate with the highest predicted sales from the plurality of planogram candidates based on the result of the prediction. The generating means generates a placement candidate indicating a candidate product to be placed in a position where one or more of the specific products can be placed on the product shelf, the candidate including at least one of the specific products. and generating the planogram candidate representing the display state including a state in which at least one of the specific commodities is arranged in the possible arrangement position indicated by the generated arrangement candidate. planogram support device. 4. The planogram support apparatus according to claim 3, wherein said generating means generates said layout candidates for all of said possible layout positions. 4. The planogram support device according to claim 3, wherein said generating means generates said arrangement candidates based on a template prepared in advance. the computer
receiving information about a product, identifying the product indicated by the received information as a specific product, and generating a plurality of planogram candidates representing display states of a plurality of products including the specific product on a product shelf;
Predicting the sales of the specific product on the plurality of planogram candidates based on relationship information representing the relationship between the positional relationship of the product on the product shelf and the sales of the product;
planogram support method. a process of receiving information about a product, identifying a product indicated by the received information as a specific product, and generating a plurality of planogram candidates representing display states of a plurality of products including the specific product on a product shelf;
a process of predicting the sales of the specific product on the plurality of planogram candidates based on the relationship information representing the relationship between the positional relationship of the product on the product shelf and the sales of the product;
A program that makes a computer run

Images